SlideShare a Scribd company logo
Recommender Systems:
A view from the trenches
Lucas Bernardi - Principal Data Scientist
lucas.bernardi@booking.com
● 28+ million reported listings
● 5.6+ million are homes, apartments and
other unique places to stay
● 141+ thousands destinations
● 1.5+ million room nights/day
● Terabytes of data every day
● 200+ Machine Learning Models Deployed
Mission to empower people to
experience the world
Recommender Systems.
Accommodations
Default Ranking
Click History
Similar Accommodations
Different Accommodations
Dates
Alternative Dates
No Dates
Available Dates
Destinations
Plain Recommendations
Autocomplete
Similar Destinations
Multi-city Trip Destinations
Nearby Destinations
More
Filters
Districts
Room Types
Policies
What do we
want to
recommend?
Recommender Systems are Complex.
Target Item Audience Framing KPI Data Feedback
Who are we
recommending?
When?
What is the role
of the recs?
How do we
measure
effectiveness?
What data are
we going to
use?
How do we
define user
satisfaction?
Recommender Systems are Hard.
Latency
Compute recs
in less than
10ms
Availability
Hotels run out of
rooms
Cold Start
New Users
New Hotels
New Types
Everyday
Most people
only travel once
a year
Sparsity Complexity
Items are
related to each
other
Offline metrics are just a Health Check.
Offline
Metric
KPI
Relative Improvements
Offline metrics are just a Health Check.
Offline
Metric
KPI
Relative Improvements
Offline metrics are just a Health Check.
Selection Bias
Models are trained using a non random
sample of the population of interest
Offline
Metric
KPI
Relative Improvements
Feedback Loops
Our Recommender System changes the
system
Non Stationarity
Suddenly everyone goes to Russia
It works in my computer but
Constraints
Hotels run out of rooms
Offline metrics are just a Health Check.
Evaluate Systems as a whole
Including the model, the UI, and the
audience
Expose wrong intuitions
More clicks is better, is it?
Show Improvement Direction
Analysing experiment results we can get
concrete ideas about what to do next
Discover Causal Effects
Experiments are the ultimate piece of
evidence for causality
Run Experiments
Offline
Metric
KPI
Relative Improvements
Latency
A very Important
Commercial Metric
Another very Important
Commercial Metric
Latency is Critical.
Latency is Critical.
Precomputed vs Online
Latency
A very Important
Commercial Metric
Another very Important
Commercial Metric
Sparse vs Dense
Black Box vs White Box
Client Side vs Server Side
Work closely with Engineers
Latency is Critical.
Decouple Training from Prediction
Centralized Repository of
Machine Learned Models
Latency
A very Important
Commercial Metric
Another very Important
Commercial Metric
Every model runs within latency constraints,
or does not run at all
Wide range of model packaging options
Centralized Monitoring of the system as a
whole
UX Matters.
2015
UX Matters.
2015 2017
UX Matters.
2015 2017
Time
UX Matters.
Work closely with UX Experts, Designers and Copywriters
Impact
Time
2015 2017
Simplicity Bias.
Tree Based
Models
Matrix
Factorization
Neural NetsMarkov ChainsGLMs
Complexity
Simplicity Bias.
Tree Based
Models
Matrix
Factorization
Neural NetsMarkov ChainsGLMs
Simple beats Complex
Success
Complexity
Beyond Ranking.
Beyond Ranking.
Augmented Recommender Systems
A view from the trenches.
Run
Experiments
Latency is
Critical
UX Matters Simple beats
Complex
Augmented
Recommenders
Thank you!
booking.ai

More Related Content

Similar to Lucas Bernardi "Рекомендаційні системи: Погляд із середини"

Telling the Full Story: Adding Qualitative Data To Executive Dashboards
Telling the Full Story: Adding Qualitative Data To Executive DashboardsTelling the Full Story: Adding Qualitative Data To Executive Dashboards
Telling the Full Story: Adding Qualitative Data To Executive Dashboards
UserZoom
 
Supercharge Your Corporate Dashboards With UX Analytics
Supercharge Your Corporate Dashboards With UX AnalyticsSupercharge Your Corporate Dashboards With UX Analytics
Supercharge Your Corporate Dashboards With UX Analytics
UserZoom
 
Optimizing Mobile UX Design Webinar Presentation Slides
Optimizing Mobile UX Design Webinar Presentation SlidesOptimizing Mobile UX Design Webinar Presentation Slides
Optimizing Mobile UX Design Webinar Presentation Slides
UserZoom
 

Similar to Lucas Bernardi "Рекомендаційні системи: Погляд із середини" (20)

How Euroflorist is preparing for Artificial Intelligence
How Euroflorist is preparing for Artificial IntelligenceHow Euroflorist is preparing for Artificial Intelligence
How Euroflorist is preparing for Artificial Intelligence
 
Data-Driven UI/UX Design with A/B Testing
Data-Driven UI/UX Design with A/B TestingData-Driven UI/UX Design with A/B Testing
Data-Driven UI/UX Design with A/B Testing
 
The Ultimate Paid PPC Tools Showdown
The Ultimate Paid PPC Tools ShowdownThe Ultimate Paid PPC Tools Showdown
The Ultimate Paid PPC Tools Showdown
 
Uz big design talk may10
Uz big design talk may10Uz big design talk may10
Uz big design talk may10
 
Telling the Full Story: Adding Qualitative Data To Executive Dashboards
Telling the Full Story: Adding Qualitative Data To Executive DashboardsTelling the Full Story: Adding Qualitative Data To Executive Dashboards
Telling the Full Story: Adding Qualitative Data To Executive Dashboards
 
Condensed testing syrup - @OptimiseorDie @sydney sep 2011 - 4 years of testin...
Condensed testing syrup - @OptimiseorDie @sydney sep 2011 - 4 years of testin...Condensed testing syrup - @OptimiseorDie @sydney sep 2011 - 4 years of testin...
Condensed testing syrup - @OptimiseorDie @sydney sep 2011 - 4 years of testin...
 
Post Click Marketing: Optimizing Conversions
Post Click Marketing: Optimizing ConversionsPost Click Marketing: Optimizing Conversions
Post Click Marketing: Optimizing Conversions
 
PQF Overview
PQF OverviewPQF Overview
PQF Overview
 
Preparing for AI - Measurefest
Preparing for AI - MeasurefestPreparing for AI - Measurefest
Preparing for AI - Measurefest
 
User Zoom Webinar Monster Aug09 Vf
User Zoom Webinar Monster Aug09 VfUser Zoom Webinar Monster Aug09 Vf
User Zoom Webinar Monster Aug09 Vf
 
NTC17 For the Love of Volunteers.pptx
NTC17   For the Love of Volunteers.pptxNTC17   For the Love of Volunteers.pptx
NTC17 For the Love of Volunteers.pptx
 
Conversion Rate Optimization for Business Growth
Conversion Rate Optimization for Business GrowthConversion Rate Optimization for Business Growth
Conversion Rate Optimization for Business Growth
 
Remote usability testing & the UCD Process webinar
Remote usability testing & the UCD Process webinarRemote usability testing & the UCD Process webinar
Remote usability testing & the UCD Process webinar
 
Preparing for Peak in Ecommerce | eTail Asia 2020
Preparing for Peak in Ecommerce | eTail Asia 2020Preparing for Peak in Ecommerce | eTail Asia 2020
Preparing for Peak in Ecommerce | eTail Asia 2020
 
Coradiant
CoradiantCoradiant
Coradiant
 
Supercharge Your Corporate Dashboards With UX Analytics
Supercharge Your Corporate Dashboards With UX AnalyticsSupercharge Your Corporate Dashboards With UX Analytics
Supercharge Your Corporate Dashboards With UX Analytics
 
Optimizing Mobile UX Design Webinar Presentation Slides
Optimizing Mobile UX Design Webinar Presentation SlidesOptimizing Mobile UX Design Webinar Presentation Slides
Optimizing Mobile UX Design Webinar Presentation Slides
 
How to Run a Data Driven Product Dev Organization by Skedulo CPM
How to Run a Data Driven Product Dev Organization by Skedulo CPMHow to Run a Data Driven Product Dev Organization by Skedulo CPM
How to Run a Data Driven Product Dev Organization by Skedulo CPM
 
Time-to-Event Models, presented by DataSong and Revolution Analytics
Time-to-Event Models, presented by DataSong and Revolution AnalyticsTime-to-Event Models, presented by DataSong and Revolution Analytics
Time-to-Event Models, presented by DataSong and Revolution Analytics
 
Transitioning from Excel to a Revenue Management System
Transitioning from Excel to a Revenue Management SystemTransitioning from Excel to a Revenue Management System
Transitioning from Excel to a Revenue Management System
 

More from Lviv Startup Club

More from Lviv Startup Club (20)

Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
 
Maksym Vyshnivetskyi: PMO Quality Management (UA)
Maksym Vyshnivetskyi: PMO Quality Management (UA)Maksym Vyshnivetskyi: PMO Quality Management (UA)
Maksym Vyshnivetskyi: PMO Quality Management (UA)
 
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
 
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
 
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
 
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
 
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
 
Igor Protsenko: Difference between outsourcing and product companies for prod...
Igor Protsenko: Difference between outsourcing and product companies for prod...Igor Protsenko: Difference between outsourcing and product companies for prod...
Igor Protsenko: Difference between outsourcing and product companies for prod...
 
Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...
 
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
 
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
 
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
 
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
 
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
 
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
 
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
 
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
 
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
 
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
 
Nikita Artemchuk: Навчання та розвиток продакт менеджера (UA)
Nikita Artemchuk: Навчання та розвиток продакт менеджера (UA)Nikita Artemchuk: Навчання та розвиток продакт менеджера (UA)
Nikita Artemchuk: Навчання та розвиток продакт менеджера (UA)
 

Recently uploaded

Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdf
Kamal Acharya
 
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsRS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
Atif Razi
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdf
Kamal Acharya
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
Neometrix_Engineering_Pvt_Ltd
 

Recently uploaded (20)

fundamentals of drawing and isometric and orthographic projection
fundamentals of drawing and isometric and orthographic projectionfundamentals of drawing and isometric and orthographic projection
fundamentals of drawing and isometric and orthographic projection
 
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical EngineeringIntroduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
 
shape functions of 1D and 2 D rectangular elements.pptx
shape functions of 1D and 2 D rectangular elements.pptxshape functions of 1D and 2 D rectangular elements.pptx
shape functions of 1D and 2 D rectangular elements.pptx
 
A CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT.pdf
A CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT.pdfA CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT.pdf
A CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT.pdf
 
Introduction to Casting Processes in Manufacturing
Introduction to Casting Processes in ManufacturingIntroduction to Casting Processes in Manufacturing
Introduction to Casting Processes in Manufacturing
 
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxCloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
 
2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdf
 
Explosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdfExplosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdf
 
Toll tax management system project report..pdf
Toll tax management system project report..pdfToll tax management system project report..pdf
Toll tax management system project report..pdf
 
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsRS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
 
Democratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek AryaDemocratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek Arya
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdf
 
Top 13 Famous Civil Engineering Scientist
Top 13 Famous Civil Engineering ScientistTop 13 Famous Civil Engineering Scientist
Top 13 Famous Civil Engineering Scientist
 
ASME IX(9) 2007 Full Version .pdf
ASME IX(9)  2007 Full Version       .pdfASME IX(9)  2007 Full Version       .pdf
ASME IX(9) 2007 Full Version .pdf
 
Online resume builder management system project report.pdf
Online resume builder management system project report.pdfOnline resume builder management system project report.pdf
Online resume builder management system project report.pdf
 
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
 
Final project report on grocery store management system..pdf
Final project report on grocery store management system..pdfFinal project report on grocery store management system..pdf
Final project report on grocery store management system..pdf
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
 
Quality defects in TMT Bars, Possible causes and Potential Solutions.
Quality defects in TMT Bars, Possible causes and Potential Solutions.Quality defects in TMT Bars, Possible causes and Potential Solutions.
Quality defects in TMT Bars, Possible causes and Potential Solutions.
 

Lucas Bernardi "Рекомендаційні системи: Погляд із середини"

  • 1. Recommender Systems: A view from the trenches Lucas Bernardi - Principal Data Scientist lucas.bernardi@booking.com
  • 2. ● 28+ million reported listings ● 5.6+ million are homes, apartments and other unique places to stay ● 141+ thousands destinations ● 1.5+ million room nights/day ● Terabytes of data every day ● 200+ Machine Learning Models Deployed Mission to empower people to experience the world
  • 3. Recommender Systems. Accommodations Default Ranking Click History Similar Accommodations Different Accommodations Dates Alternative Dates No Dates Available Dates Destinations Plain Recommendations Autocomplete Similar Destinations Multi-city Trip Destinations Nearby Destinations More Filters Districts Room Types Policies
  • 4. What do we want to recommend? Recommender Systems are Complex. Target Item Audience Framing KPI Data Feedback Who are we recommending? When? What is the role of the recs? How do we measure effectiveness? What data are we going to use? How do we define user satisfaction?
  • 5. Recommender Systems are Hard. Latency Compute recs in less than 10ms Availability Hotels run out of rooms Cold Start New Users New Hotels New Types Everyday Most people only travel once a year Sparsity Complexity Items are related to each other
  • 6. Offline metrics are just a Health Check. Offline Metric KPI Relative Improvements
  • 7. Offline metrics are just a Health Check. Offline Metric KPI Relative Improvements
  • 8. Offline metrics are just a Health Check. Selection Bias Models are trained using a non random sample of the population of interest Offline Metric KPI Relative Improvements Feedback Loops Our Recommender System changes the system Non Stationarity Suddenly everyone goes to Russia It works in my computer but Constraints Hotels run out of rooms
  • 9. Offline metrics are just a Health Check. Evaluate Systems as a whole Including the model, the UI, and the audience Expose wrong intuitions More clicks is better, is it? Show Improvement Direction Analysing experiment results we can get concrete ideas about what to do next Discover Causal Effects Experiments are the ultimate piece of evidence for causality Run Experiments Offline Metric KPI Relative Improvements
  • 10. Latency A very Important Commercial Metric Another very Important Commercial Metric Latency is Critical.
  • 11. Latency is Critical. Precomputed vs Online Latency A very Important Commercial Metric Another very Important Commercial Metric Sparse vs Dense Black Box vs White Box Client Side vs Server Side Work closely with Engineers
  • 12. Latency is Critical. Decouple Training from Prediction Centralized Repository of Machine Learned Models Latency A very Important Commercial Metric Another very Important Commercial Metric Every model runs within latency constraints, or does not run at all Wide range of model packaging options Centralized Monitoring of the system as a whole
  • 16. UX Matters. Work closely with UX Experts, Designers and Copywriters Impact Time 2015 2017
  • 18. Simplicity Bias. Tree Based Models Matrix Factorization Neural NetsMarkov ChainsGLMs Simple beats Complex Success Complexity
  • 21. A view from the trenches. Run Experiments Latency is Critical UX Matters Simple beats Complex Augmented Recommenders